ebook2audiobook
Local audiobook converter turns ebooks into narrated audio with chapters and voice cloning. Runs on Windows, macOS and Linux under Apache 2.0.
ebook2audiobook turns non-DRM ebooks into narrated audio with chapters and metadata, for readers who want audio editions of their own books. It runs locally on Windows, macOS and Linux, with Docker support and a browser interface built with Gradio. It's open source under Apache 2.0.
Voice cloning lets you use an audio recording as the narrator, and the tool can clean background noise or music from the reference recording. Supported speech engines include XTTSv2, Bark, Fairseq, VITS, Tacotron2, Tortoise, GlowTTS and YourTTS. You can also use custom trained models or supplied fine-tuned presets. Language support depends on the engine, with options including English, Chinese, Arabic, Hindi and Swahili.
Input support covers EPUB, MOBI, PDF, Word documents and plain text, while OCR extracts text from scanned pages and images. EPUB and MOBI give the best results for automatic chapter detection. It also reads short text. Output formats include M4B, MP3, FLAC and WAV, in mono or stereo. For narration that needs more control, SML tags specify pauses and voice changes within the text.
Batch conversion and a command-line mode suit larger book collections, and interrupted conversions can resume. The tool can translate an ebook with Argos Translate before generating speech and connect to an Audiobookshelf server. It supports CPU processing and acceleration through CUDA, ROCm, Intel XPU, Jetson and Apple Silicon MPS. Minimum requirements are 2 GB RAM and, for GPU use, 1 GB VRAM; modern speech engines can be very slow on CPU.
